Method and system for online control of an electric dust precipitation system

Abstract

The embodiment of the present application provides an online control method and system of an electric dust removal system, and belongs to the technical field of electric dust removal. The method comprises the following steps: collecting real-time operation parameters of the electric dust removal system, and simulating operation conditions based on the real-time operation parameters; determining condition fitting parameters of each preset fitting path based on the simulated conditions; taking dust removal efficiency as an optimization target, taking each fitting path as an optimization variable to construct an optimization problem; adaptively adjusting the condition fitting parameters of each preset fitting path, determining an optimization path based on the linkage condition of the optimization problem, and determining target parameters of the optimization path based on the optimization problem; and generating and executing corresponding control instructions based on the target parameters of the optimization path. The present application scheme ensures accuracy while improving the intelligence of the system when performing electric dust removal efficiency control.

Description

Technical Field

[0001] This invention relates to the field of electrostatic precipitator technology, specifically to an online control method and an online control system for an electrostatic precipitator system. Background Technology

[0002] Electrostatic precipitators (ESPs) are crucial environmental protection systems in thermal power units. Their primary function is to adsorb and remove solid dust particles from flue gas, reducing dust emissions and ensuring clean emissions from the power plant. Various factors influence ESP efficiency, and precise control often requires simultaneous adjustments to these influencing factors. However, current solutions heavily rely on manual experience for efficiency adjustments, necessitating subjective judgments based on current operating efficiency, leading to inconsistent accuracy. Furthermore, prolonged on-site monitoring is essential, resulting in significant labor costs. Moreover, the presence of multiple factors affecting ESP efficiency necessitates various adjustment combinations. Existing solutions often rely on single-mode adjustments due to the habits of monitoring personnel, resulting in poor overall system intelligence and an inability to find the most efficient adjustment. Therefore, to address the issues of insufficient adjustment accuracy and lack of intelligence in existing solutions, a new ESP control scheme is needed. Summary of the Invention

[0003] The purpose of this invention is to provide an online control method and system for an electrostatic precipitator system, so as to at least solve the problems of insufficient adjustment accuracy and poor intelligence in existing electrostatic precipitator system control schemes.

[0004] To achieve the above objectives, the first aspect of the present invention provides an online control method for an electrostatic precipitator system. The method includes: collecting real-time operating parameters of the electrostatic precipitator system and simulating operating conditions based on the real-time operating parameters; determining operating condition fitting parameters for each preset fitting path based on the simulated operating conditions; constructing an optimization problem with dust removal efficiency as the optimization objective and each fitting path as the optimization variable; adaptively adjusting the operating condition fitting parameters of each preset fitting path; determining an optimization path based on the linkage of the optimization problem; and determining the target parameters of the optimization path based on the optimization problem; and generating and executing corresponding control commands based on the target parameters of the optimization path.

[0005] Optionally, the real-time operating parameters include: unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

[0006] Optionally, in collecting the real-time operating parameters of the electrostatic precipitator system, the method further preprocesses the collected real-time operating parameters; the preprocessing includes: data cleaning, missing value handling, and data standardization.

[0007] Optionally, the preset fitting path includes: a secondary voltage fitting path, a secondary current fitting path, a rapping cycle fitting path, and a charging ratio setting fitting path.

[0008] Optionally, determining the fitting parameters for each preset fitting path based on the simulated working conditions includes: splitting the simulated working conditions into fitting paths to obtain the parameter values ​​of the next-level nodes of each fitting path, which are used as the fitting parameters for each preset fitting path; wherein each fitting path includes one first-level node and multiple second-level nodes; each second-level node includes multiple third-level nodes; each third-level node includes multiple fourth-level nodes, and each driver node corresponds to a real-time operating parameter node.

[0009] Optionally, the step of constructing an optimization problem with dust removal efficiency as the optimization objective and each fitted path as the optimization variable includes: determining the optimization problem objective based on a preset expected dust removal efficiency; determining the optimization direction and optimization amount based on the difference between the current dust removal efficiency and the preset expected dust removal efficiency; performing arbitrary combinations of each fitted path to obtain multiple multivariate arrays; constructing an optimization problem based on the optimization problem objective and the obtained multiple multivariate arrays, and using the optimization line and optimization amount as the cutoff convergence conditions of the optimization problem.

[0010] Optionally, the adaptive adjustment of the operating condition fitting parameters of each preset fitting path, determining the optimization path based on the linkage of the optimization problem, and determining the target parameters of the optimization path based on the optimization problem includes: sequentially selecting a multivariate array, dynamically adjusting the operating condition fitting parameters of the preset fitting path under each multivariate array, and determining whether there is a situation that satisfies the convergence condition; if satisfied, then the optimization path in the current multivariate array is taken as the path to be optimized, and the target parameters of the corresponding path to be optimized are obtained based on the operating condition fitting parameters of the optimization path under the preset expected dust removal efficiency; if not satisfied, then the next multivariate array is selected until a multivariate array that satisfies the convergence condition is obtained.

[0011] Optionally, the selection rule for the multivariate array is as follows: prioritize the multivariate array with the fewest elements; if there are multiple multivariate arrays with the fewest elements and the same number of elements, then any one of the multivariate arrays can be selected.

[0012] A second aspect of the present invention provides an online control system for an electrostatic precipitator system. The system includes: a data acquisition unit for acquiring real-time operating parameters of the electrostatic precipitator system and simulating operating conditions based on the real-time operating parameters; a parameter determination unit for determining operating condition fitting parameters for each preset fitting path based on the simulated operating conditions; a processing unit for constructing an optimization problem with dust removal efficiency as the optimization objective and each fitting path as the optimization variable; a path determination unit for adaptively adjusting the operating condition fitting parameters of each preset fitting path, determining an optimization path based on the linkage of the optimization problem, and determining the target parameters of the optimization path based on the optimization problem; and an execution unit for generating and executing corresponding control commands based on the target parameters of the optimization path.

[0013] On the other hand, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described online control method for an electrostatic precipitator system.

[0014] Through the above technical solution, this invention constructs an optimization problem with dust removal efficiency as the optimization objective, builds corresponding fitting paths for each influencing factor, and determines the impact of each fitting path on the electrostatic precipitator efficiency in the current scenario by obtaining the fitting results, thereby selecting the optimal adjustment path. Furthermore, the adjustment amount of the adjustment path is determined through the optimization problem, generating adjustment rules under the corresponding path, realizing a self-regulation scheme for the electrostatic precipitator system. Without manual parameters, the optimal regulation scheme can be found, achieving self-regulation of the electrostatic precipitator system. While ensuring objectivity and improving accuracy, it also enhances the intelligence of the system.

[0015] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of the steps of an online control method for an electrostatic precipitator system provided in one embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of the fitting path setting provided by one embodiment of the present invention;

[0019] Figure 3 This is a system structure diagram of an online control system for an electrostatic precipitator provided in one embodiment of the present invention. Detailed Implementation

[0020] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0021] Electrostatic precipitators (ESPs) are crucial environmental protection systems in thermal power units. Their primary function is to adsorb and remove solid dust particles from flue gas, reducing dust emissions and ensuring clean emissions from the power plant. Various factors influence the efficiency of ESPs, and precise control often requires simultaneous adjustments to these influencing factors. However, current solutions heavily rely on manual experience for efficiency adjustments, necessitating subjective judgments based on current operating efficiency, leading to inconsistent accuracy. Furthermore, prolonged on-site monitoring is essential, resulting in significant labor costs. Moreover, the presence of multiple factors affecting ESP efficiency necessitates various adjustment combinations. Existing solutions often rely on the habits of supervisors, resulting in a single-mode adjustment and poor overall system intelligence, failing to identify the most efficient solution.

[0022] To address the issues of insufficient adjustment accuracy and poor intelligence in existing solutions, this invention proposes an online control method and system for electrostatic precipitators (ESPs). This invention constructs an optimization problem with dust removal efficiency as the optimization objective, builds corresponding fitting paths for each influencing factor, and determines the impact of each fitted path on ESP efficiency in the current scenario by obtaining the fitting results, thereby selecting the optimal adjustment path. Furthermore, the adjustment amount of the adjustment path is determined through the optimization problem, generating adjustment rules for the corresponding path, realizing a self-regulating scheme for the ESP. This achieves the optimal control scheme without manual parameters, enabling the ESP to self-regulate. While ensuring objectivity and improving accuracy, this invention also enhances the system's intelligence.

[0023] Figure 1 This is a flowchart of an online control method for an electrostatic precipitator system provided in one embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides an online control method for an electrostatic precipitator system, the method comprising:

[0024] Step S10: Collect the real-time operating parameters of the electrostatic precipitator system and simulate the operating conditions based on the real-time operating parameters.

[0025] Specifically, the real-time operating parameters include: unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

[0026] In one possible implementation, the dust collector control system or DCS control system outputs the required data via a 485 serial port, using communication protocols supported by, for example, Modbus RTU or Fbox. The optimized software system uses the Modbus TCP protocol to directly collect data from the controller, including the data name, address, etc.

[0027] Preferably, to achieve online control, the present invention requires data collection and aggregation. After data is collected at the corresponding device, remote data transmission and aggregation are performed. Based on the MQTT message queue telemetry transmission protocol, the collected and optimized data are periodically or dynamically pushed. It supports IoT platforms based on the MQTT protocol, enabling quick and efficient remote data connection. It supports Ethernet, 2G, 3G, 4G, and WiFi signals, exhibiting strong environmental adaptability.

[0028] Preferably, after collecting the real-time operating parameters of the electrostatic precipitator system, the method further preprocesses the collected real-time operating parameters; the preprocessing includes: data cleaning, missing value handling, and data standardization.

[0029] In this embodiment of the invention, the environmental dust collection process often suffers from data loss and distortion due to changes in the collection environment, measurement methods, and unstable sensor networks. This data, containing noise and distortion, significantly impacts the data analysis and modeling process, ultimately degrading the final model results. Therefore, it is essential to standardize the measurement point data using appropriate methods and map it to the same data domain during the data preprocessing stage. Before data analysis and modeling, feature selection or parameter dimensionality reduction for a specific model is a crucial step in ensuring model accuracy and reducing computational costs. Furthermore, the appropriate use of feature extraction algorithms can effectively reduce the workload of feature extraction.

[0030] Step S20: Based on the simulated working conditions, determine the working condition fitting parameters for each preset fitting path.

[0031] Specifically, such as Figure 2 The preset fitting paths include: a secondary voltage fitting path, a secondary current fitting path, a rapping cycle fitting path, and a charging ratio setting fitting path. The simulated operating conditions are decomposed into fitting paths to obtain the parameter values ​​of the next-level nodes of each fitting path, which serve as the operating condition fitting parameters for each preset fitting path. Each fitting path includes one first-level node and multiple second-level nodes; each second-level node includes multiple third-level nodes; each third-level node includes multiple fourth-level nodes, and each fourth-level node corresponds to a real-time operating parameter node.

[0032] Preferably, the fitting path included in the solution of the present invention specifically includes:

[0033] 1) Primary node: Secondary voltage limit, secondary current limit, rapping cycle and charging ratio settings;

[0034] 2) Secondary nodes: changes in secondary voltage waveform, changes in secondary current waveform, changes in spark value, changes in turbidity of the outlet flue, changes in dust conditions on the electrode plates, and changes in electrode line separation;

[0035] 3) Third-level nodes: changes in electric field flue gas velocity, changes in dust charge rate, changes in dust resistivity, and changes in other dust properties;

[0036] 4) Level 4 nodes: unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

[0037] In one possible implementation, for the secondary voltage fitting path, firstly, based on unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters, the changes in electric field flue gas velocity, dust charge rate, dust resistivity, and other dust characteristics are fitted. Then, based on these changes, the secondary voltage waveform, secondary current waveform, spark value, outlet flue gas turbidity, electrode dust condition, and electrode line separation are fitted. Finally, the secondary voltage limiting change is fitted using the changes in secondary voltage waveform, secondary current waveform, spark value, and outlet flue gas turbidity.

[0038] Step S30: Construct an optimization problem with dust removal efficiency as the optimization objective and each fitted path as the optimization variable.

[0039] Specifically, based on the preset expected dust removal efficiency, the optimization problem objective is determined; based on the difference between the current dust removal efficiency and the preset expected dust removal efficiency, the optimization direction and optimization amount are determined; various fitting paths are arbitrarily combined to obtain multiple multivariate arrays; based on the optimization problem objective and the obtained multiple multivariate arrays, the optimization problem is constructed, and the optimization line and optimization amount are used as the cutoff convergence conditions of the optimization problem.

[0040] In this embodiment of the invention, as explained above, there may be multiple control schemes for dust removal efficiency. For example, only the secondary voltage and secondary current can be controlled, while keeping the rapping cycle and charging ratio constant. Another example is adjusting the secondary voltage, secondary current, and rapping cycle simultaneously, while keeping the charging ratio constant. Theoretically, the fewer parameters adjusted, the higher the adjustment accuracy and efficiency, and the lower the corresponding execution difficulty. To achieve the adjustment of the overall scheme, various arrays are combined, including binary arrays, ternary arrays, and quaternary arrays. The corresponding binary array is the combination relationship of any two fitted paths. If there are four fitted paths, then 6 binary arrays, 3 ternary arrays, and 1 quaternary array are generated.

[0041] Step S40: Adaptively adjust the working condition fitting parameters of each preset fitting path, determine the optimization path based on the linkage of the optimization problem, and determine the target parameters of the optimization path based on the optimization problem.

[0042] Specifically, the multivariate arrays are selected sequentially, and the working condition fitting parameters of the preset fitting path under each multivariate array are dynamically adjusted. It is then determined whether there is a situation that meets the convergence condition. If it does, the optimized path in the current multivariate array is taken as the path to be optimized, and the target parameters of the corresponding path to be optimized are obtained based on the working condition fitting parameters of the optimized path under the preset expected dust removal efficiency. If it does not meet the condition, the next multivariate array is selected until a multivariate array that meets the convergence condition is obtained.

[0043] In this embodiment of the invention, each multivariate array is evaluated to find an adjustment path suitable for the current operating conditions, so that parameters can be adjusted for the path to achieve dust removal efficiency adjustment. If a multivariate array that meets the convergence condition is found, it means that the fitted paths contained in the multivariate array can be combined to achieve the condition of adjusting the dust removal efficiency to the desired efficiency.

[0044] Preferably, the selection rule for the multivariate array is as follows: the multivariate array with the fewest elements is selected first; if there are multiple multivariate arrays with the fewest elements and the same number of elements, then any one of the multivariate arrays can be selected.

[0045] In this embodiment of the invention, in order to improve adjustment efficiency and ensure response speed, the preferred approach for adjusting dust removal efficiency is to use a method that involves fewer parameter adjustments. Therefore, the convergence condition is first determined by the least number of elements in the multivariate array. If the convergence condition is met, no further judgment is needed, and the least path adjustment can be performed directly.

[0046] Step S50: Based on the target parameters of the optimized path, generate and execute the corresponding control instructions.

[0047] Specifically, once the target parameters are determined, the fitting path selected accordingly can be adjusted to achieve the desired parameters. As long as the target parameters of the fitting path are met, the final coupling effect (i.e., dust removal efficiency) will also meet the expectations.

[0048] Figure 3 This is a system structure diagram of an online control system for an electrostatic precipitator provided in one embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an online control system for an electrostatic precipitator system, the system comprising:

[0049] The data acquisition unit is used to acquire real-time operating parameters of the electrostatic precipitator system and to simulate operating conditions based on the real-time operating parameters.

[0050] The real-time operating parameters include: unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

[0051] In one possible implementation, the dust collector control system or DCS control system outputs the required data via a 485 serial port, using communication protocols supported by, for example, Modbus RTU or Fbox. The optimized software system uses the Modbus TCP protocol to directly collect data from the controller, including the data name, address, etc.

[0052] Preferably, to achieve online control, the present invention requires data collection and aggregation. After data is collected at the corresponding device, remote data transmission and aggregation are performed. Based on the MQTT message queue telemetry transmission protocol, the collected and optimized data are periodically or dynamically pushed. It supports IoT platforms based on the MQTT protocol, enabling quick and efficient remote data connection. It supports Ethernet, 2G, 3G, 4G, and WiFi signals, exhibiting strong environmental adaptability. Preferably, the data acquisition module integrates RS232 and RS485 serial ports, supporting Modbus RTU, CAN bus, and various PLC system internal communication protocols; the integrated Ethernet port supports over 300 industrial communication protocols, including Modbus TCP, S7-300 Network, AB Compactlogix_Ciptag, and GERX3i_SRTP.

[0053] Edge software can be used to perform edge optimization processing on the collected data, and can record the status of switch signals, configure alarms, etc.; it can perform linear conversion, range setting, upper and lower limit alarm setting, historical record and historical alarm record processing on analog data.

[0054] The data acquisition module supports Ethernet or 4G networks, and can be remotely configured and monitored on the edge gateway management platform.

[0055] Preferably, after collecting the real-time operating parameters of the electrostatic precipitator system, the method further preprocesses the collected real-time operating parameters; the preprocessing includes: data cleaning, missing value handling, and data standardization.

[0056] In this embodiment of the invention, the environmental dust collection process often suffers from data loss and distortion due to changes in the collection environment, measurement methods, and unstable sensor networks. This data, containing noise and distortion, significantly impacts the data analysis and modeling process, ultimately degrading the final model results. Therefore, it is essential to standardize the measurement point data using appropriate methods and map it to the same data domain during the data preprocessing stage. Before data analysis and modeling, feature selection or parameter dimensionality reduction for a specific model is a crucial step in ensuring model accuracy and reducing computational costs. Furthermore, the appropriate use of feature extraction algorithms can effectively reduce the workload of feature extraction.

[0057] The parameter determination unit is used to determine the working condition fitting parameters for each preset fitting path based on the simulated working conditions.

[0058] Specifically, the preset fitting paths include: a secondary voltage fitting path, a secondary current fitting path, a rapping cycle fitting path, and a charging ratio setting fitting path. The simulated operating conditions are decomposed into fitting paths to obtain the parameter values ​​of the next-level nodes of each fitting path, which serve as the operating condition fitting parameters for each preset fitting path. Each fitting path includes one first-level node and multiple second-level nodes; each second-level node includes multiple third-level nodes; each third-level node includes multiple fourth-level nodes, and each fourth-level node corresponds to a real-time operating parameter node.

[0059] Preferably, the fitting path included in the solution of the present invention specifically includes:

[0060] 1) Primary node: Secondary voltage limit, secondary current limit, rapping cycle and charging ratio settings;

[0061] 2) Secondary nodes: changes in secondary voltage waveform, changes in secondary current waveform, changes in spark value, changes in turbidity of the outlet flue, changes in dust conditions on the electrode plates, and changes in electrode line separation;

[0062] 3) Third-level nodes: changes in electric field flue gas velocity, changes in dust charge rate, changes in dust resistivity, and changes in other dust properties;

[0063] 4) Level 4 nodes: unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

[0064] In one possible implementation, for the secondary voltage fitting path, firstly, based on unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters, the changes in electric field flue gas velocity, dust charge rate, dust resistivity, and other dust characteristics are fitted. Then, based on these changes, the secondary voltage waveform, secondary current waveform, spark value, outlet flue gas turbidity, electrode dust condition, and electrode line separation are fitted. Finally, the secondary voltage limiting change is fitted using the changes in secondary voltage waveform, secondary current waveform, spark value, and outlet flue gas turbidity.

[0065] The processing unit is used to construct an optimization problem with dust removal efficiency as the optimization objective and each fitted path as the optimization variable.

[0066] Specifically, based on the preset expected dust removal efficiency, the optimization problem objective is determined; based on the difference between the current dust removal efficiency and the preset expected dust removal efficiency, the optimization direction and optimization amount are determined; various fitting paths are arbitrarily combined to obtain multiple multivariate arrays; based on the optimization problem objective and the obtained multiple multivariate arrays, the optimization problem is constructed, and the optimization line and optimization amount are used as the cutoff convergence conditions of the optimization problem.

[0067] In this embodiment of the invention, as explained above, there may be multiple control schemes for dust removal efficiency. For example, only the secondary voltage and secondary current can be controlled, while keeping the rapping cycle and charging ratio constant. Another example is adjusting the secondary voltage, secondary current, and rapping cycle simultaneously, while keeping the charging ratio constant. Theoretically, the fewer parameters adjusted, the higher the adjustment accuracy and efficiency, and the lower the corresponding execution difficulty. To achieve the adjustment of the overall scheme, various arrays are combined, including binary arrays, ternary arrays, and quaternary arrays. The corresponding binary array is the combination relationship of any two fitted paths. If there are four fitted paths, then 6 binary arrays, 3 ternary arrays, and 1 quaternary array are generated.

[0068] The path determination unit is used to adaptively adjust the working condition fitting parameters of each preset fitting path, determine the optimization path based on the linkage of the optimization problem, and determine the target parameters of the optimization path based on the optimization problem.

[0069] Specifically, the multivariate arrays are selected sequentially, and the working condition fitting parameters of the preset fitting path under each multivariate array are dynamically adjusted. It is then determined whether there is a situation that meets the convergence condition. If it does, the optimized path in the current multivariate array is taken as the path to be optimized, and the target parameters of the corresponding path to be optimized are obtained based on the working condition fitting parameters of the optimized path under the preset expected dust removal efficiency. If it does not meet the condition, the next multivariate array is selected until a multivariate array that meets the convergence condition is obtained.

[0070] In this embodiment of the invention, each multivariate array is evaluated to find an adjustment path suitable for the current operating conditions, so that parameters can be adjusted for the path to achieve dust removal efficiency adjustment. If a multivariate array that meets the convergence condition is found, it means that the fitted paths contained in the multivariate array can be combined to achieve the condition of adjusting the dust removal efficiency to the desired efficiency.

[0071] Preferably, the selection rule for the multivariate array is as follows: the multivariate array with the fewest elements is selected first; if there are multiple multivariate arrays with the fewest elements and the same number of elements, then any one of the multivariate arrays can be selected.

[0072] In this embodiment of the invention, in order to improve adjustment efficiency and ensure response speed, the preferred approach for adjusting dust removal efficiency is to use a method that involves fewer parameter adjustments. Therefore, the convergence condition is first determined by the least number of elements in the multivariate array. If the convergence condition is met, no further judgment is needed, and the least path adjustment can be performed directly.

[0073] The execution unit is used to generate and execute corresponding control instructions based on the target parameters of the optimized path.

[0074] Specifically, once the target parameters are determined, the fitting path selected accordingly can be adjusted to achieve the desired parameters. As long as the target parameters of the fitting path are met, the final coupling effect (i.e., dust removal efficiency) will also meet the expectations.

[0075] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described online control method for an electrostatic precipitator system.

[0076] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0077] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0078] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. An online control method for an electrostatic precipitator system, characterized in that, The method includes: Collect real-time operating parameters of the electrostatic precipitator system and simulate operating conditions based on the real-time operating parameters; Based on simulated operating conditions, the operating condition fitting parameters for each preset fitting path are determined; among them, The preset fitting path includes: secondary voltage fitting path, secondary current fitting path, rapping cycle fitting path, and charging ratio setting fitting path. Based on the simulated working conditions, the working condition fitting parameters for each preset fitting path are determined, including: splitting the simulated working conditions into fitting paths to obtain the parameter values ​​of the next-level nodes of each fitting path, which are used as the working condition fitting parameters for each preset fitting path; wherein, each fitting path includes one first-level node and multiple second-level nodes; each second-level node includes multiple third-level nodes; each third-level node includes multiple fourth-level nodes, and each fourth-level node corresponds to a real-time running parameter node. Based on the preset expected dust removal efficiency, the objective of the optimization problem is determined; based on the difference between the current dust removal efficiency and the preset expected dust removal efficiency, the optimization direction and optimization amount are determined; various fitting paths are arbitrarily combined to obtain multiple multivariate arrays; based on the optimization problem objective and the obtained multiple multivariate arrays, the optimization problem is constructed, and the optimization direction and optimization amount are used as the cutoff convergence conditions of the optimization problem. Adaptively adjust the working condition fitting parameters of each preset fitting path, determine the optimization path based on the linkage of the optimization problem, and determine the target parameters of the optimization path based on the optimization problem; including: Select the multivariate arrays in sequence, dynamically adjust the working condition fitting parameters of the preset fitting path under each multivariate array, and determine whether there is a situation that meets the convergence condition. If it does, the optimized path in the current multivariate array is taken as the path to be optimized, and the target parameters of the corresponding path to be optimized are obtained based on the working condition fitting parameters of the optimized path under the preset expected dust removal efficiency. If it does not meet the condition, select the next multivariate array until a multivariate array that meets the convergence condition is obtained. Based on the target parameters of the optimized path, corresponding control instructions are generated and executed.

2. The method according to claim 1, characterized in that, The real-time operating parameters include: Unit load parameters, flue gas volume parameters, denitrification efficiency parameters, ammonia slip parameters, flue gas composition parameters, and flue gas temperature parameters.

3. The method according to claim 1, characterized in that, After collecting the real-time operating parameters of the electrostatic precipitator system, the method further preprocesses the collected real-time operating parameters. The preprocessing includes: Data cleaning, missing value handling, and data standardization.

4. The method according to claim 1, characterized in that, The selection rules for the multivariate array are as follows: Prioritize selecting the multivariate array with the fewest elements; If there are multiple multi-element arrays with the smallest number of elements and the same number of elements, then any one of the multi-element arrays can be selected.

5. An online control system for an electrostatic precipitator system, characterized in that, The system is used to execute the online control method for the electrostatic precipitator system according to any one of claims 1-4, and the system comprises: The data acquisition unit is used to acquire real-time operating parameters of the electrostatic precipitator system and to simulate operating conditions based on the real-time operating parameters. The parameter determination unit is used to determine the working condition fitting parameters for each preset fitting path based on the simulated working conditions. The processing unit is used to construct an optimization problem with dust removal efficiency as the optimization objective and each fitted path as the optimization variable. The path determination unit is used to adaptively adjust the working condition fitting parameters of each preset fitting path, determine the optimization path based on the linkage of the optimization problem, and determine the target parameters of the optimization path based on the optimization problem. The execution unit is used to generate and execute corresponding control instructions based on the target parameters of the optimized path.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the online control method for the electrostatic precipitator system as described in any one of claims 1-4.

Images